Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions and assertions related to obligations, conditions, and actions in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of conditional or interrogative phrases related to legal decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whoſe
    -0.82
     myſelf
    -0.73
     Reſ
    -0.72
     ſeveral
    -0.71
     itſelf
    -0.70
     themſelves
    -0.69
     Monfieur
    -0.69
     Houſe
    -0.68
    ]--;
    -0.67
     Diſ
    -0.67
    POSITIVE LOGITS
    InvalidProtocol
    0.48
    .
    0.48
     did
    0.47
     hacerlo
    0.47
     so
    0.47
    PointerException
    0.45
    Gweler
    0.45
     Mont
    0.43
    loxy
    0.43
    چھ
    0.43
    Act Density 0.359%

    No Known Activations